SOTAVerified

Visual Question Answering

MLLM Leaderboard

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1501–1550 of 2177 papers

TitleStatusHype
Dual Capsule Attention Mask Network with Mutual Learning for Visual Question Answering—0
A Dual-Attention Learning Network with Word and Sentence Embedding for Medical Visual Question AnsweringCode0
On the Effects of Video Grounding on Language Models—0
Task Formulation Matters When Learning Continually: A Case Study in Visual Question AnsweringCode0
RepsNet: Combining Vision with Language for Automated Medical Reports—0
Exploring Modulated Detection Transformer as a Tool for Action Recognition in VideosCode0
Continual VQA for Disaster Response SystemsCode0
Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering—0
Overcoming Language Priors in Visual Question Answering via Distinguishing Superficially Similar InstancesCode0
LAVIS: A Library for Language-Vision Intelligence—0
Correlation Information Bottleneck: Towards Adapting Pretrained Multimodal Models for Robust Visual Question Answering—0
MUST-VQA: MUltilingual Scene-text VQA—0
PaLI: A Jointly-Scaled Multilingual Language-Image Model—0
PreSTU: Pre-Training for Scene-Text Understanding—0
Pre-training image-language transformers for open-vocabulary tasks—0
Improving the Cross-Lingual Generalisation in Visual Question AnsweringCode0
Bidirectional Contrastive Split Learning for Visual Question Answering—0
FashionVQA: A Domain-Specific Visual Question Answering System—0
How good are deep models in understanding the generated images?—0
Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language TasksCode0
VLMAE: Vision-Language Masked Autoencoder—0
ILLUME: Rationalizing Vision-Language Models through Human InteractionsCode0
Understanding Attention for Vision-and-Language TasksCode0
Aesthetic Visual Question Answering of Photographs—0
Uncertainty-based Visual Question Answering: Estimating Semantic Inconsistency between Image and Knowledge Base—0
Is GPT-3 all you need for Visual Question Answering in Cultural Heritage?—0
Towards Complex Document Understanding By Discrete Reasoning—0
WinoGAViL: Gamified Association Benchmark to Challenge Vision-and-Language ModelsCode0
Visual Perturbation-aware Collaborative Learning for Overcoming the Language Prior Problem—0
Semantic-aware Modular Capsule Routing for Visual Question Answering—0
OVQA: A Clinically Generated Visual Question Answering Dataset—0
Knowing Earlier what Right Means to You: A Comprehensive VQA Dataset for Grounding Relative Directions via Multi-Task LearningCode0
VGNMN: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems—0
American == White in Multimodal Language-and-Image AI—0
Modern Question Answering Datasets and Benchmarks: A Survey—0
EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering—0
From Shallow to Deep: Compositional Reasoning over Graphs for Visual Question Answering—0
VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason ObjectivesCode0
Tell Me the Evidence? Dual Visual-Linguistic Interaction for Answer Grounding—0
Grounding Answers for Visual Questions Asked by Visually Impaired People—0
Test-Time Adaptation for Visual Document Understanding—0
Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model—0
cViL: Cross-Lingual Training of Vision-Language Models using Knowledge DistillationCode0
From Pixels to Objects: Cubic Visual Attention for Visual Question Answering—0
VL-BEiT: Generative Vision-Language Pretraining—0
Structured Two-stream Attention Network for Video Question Answering—0
Question Modifiers in Visual Question Answering—0
Fine-tuning vs From Scratch: Do Vision & Language Models Have Similar Capabilities on Out-of-Distribution Visual Question Answering?—0
Un jeu de données pour répondre à des questions visuelles à propos d’entités nommées en utilisant des bases de connaissances (ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities)—0
Visual Superordinate Abstraction for Robust Concept Learning—0
Show:102550
← PrevPage 31 of 44Next →
All datasetsMM-VetViP-BenchVQA v2 test-devBenchLMMMMBenchV*benchVQA v2 valMSRVTT-QAVQA v2 test-stdMMHal-BenchMSVD-QAPlotQA-D1

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMCTAgent (GPT-4 + GPT-4V)GPT-4 score74.24—Unverified
2Qwen2-VL-72BGPT-4 score74—Unverified
3InternVL2.5-78BGPT-4 score72.3—Unverified
4GPT-4o +text rationale +IoTGPT-4 score72.2—Unverified
5Lyra-ProGPT-4 score71.4—Unverified
6GLM-4V-PlusGPT-4 score71.1—Unverified
7Phantom-7BGPT-4 score70.8—Unverified
8InternVL2.5-38BGPT-4 score68.8—Unverified
9InternVL2-26B (SGP, token ratio 64%)GPT-4 score65.6—Unverified
10Baichuan-Omni (7B)GPT-4 score65.4—Unverified